April 18, 2017
1 min read

EHR algorithms help researchers identify patients with lupus

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

Researchers have developed electronic health record algorithms to identify patients with lupus, according to published data.

“We found that using only ICD-9 billing codes to identify patients with systemic lupus erythematosus (SLE) within the electronic health record (EHR) was not accurate,” April Barnado, MD, at Vanderbilt University Medical Center, told Healio Rheumatology. “We developed and validated the first algorithms that incorporate lab values and medications with the SLE ICD-9 code to identify patients with SLE accurately in the EHR with positive predictive values ranging from 89-95%.”

April Barnado
April Barnado

Barnado and colleagues used Vanderbilt’s Synthetic Derivative, a de-identified electronic health record (EHR) that included 2.5 million individuals, to identify 5,959 patients with at least one systemic lupus erythematosus (SLE) ICD-9 code — as diagnosed by a rheumatologist, nephrologist or dermatologist — from which 200 were selected to create a training set. Researchers calculated positive predictive values and sensitivity for combinations of code counts of the SLE ICD-9, a positive antinuclear antibody, use of medications and a lupus keyword in the problem list.

The algorithm, which included three or more counts of SLE ICD-9 code, at least 1:40 antinuclear antibody positivity and use of both disease-modifying antirheumatic drugs and steroids, had the highest PPV, which was 95% in the training set and 91% in the validation set.

“These algorithms represent powerful tools to enable researchers to identify and study SLE patients accurately in the EHR,” Barnado said. – by Will Offit

Disclosure: The researchers report no relevant financial disclosures.